Related papers: Safely Abstracting Memory Layouts
The security and efficiency of modern computing systems are fundamentally undermined by the absence of a native architectural mechanism to propagate high-level program semantics, such as object identity, bounds, and lifetime, across the…
Memory-augmented Large Language Models (LLMs) have demonstrated remarkable capability for complex and long-horizon embodied planning. By keeping track of past experiences and environmental states, memory enables LLMs to maintain a global…
In this paper, we introduce a novel framework for memory-efficient and privacy-preserving continual learning in 3D object classification. Unlike conventional memory-based approaches in continual learning that require storing numerous…
Simultaneous localization and mapping (SLAM) with implicit neural representations has received extensive attention due to the expressive representation power and the innovative paradigm of continual learning. However, deploying such a…
We present a methodology for formulating simplifying abstractions in machine learning systems by identifying and harnessing the utility structure of decisions. Machine learning tasks commonly involve high-dimensional output spaces (e.g.,…
The expanding hardware diversity in high performance computing adds enormous complexity to scientific software development. Developers who aim to write maintainable software have two options: 1) To use a so-called data locality abstraction…
Understanding 3D object shapes necessitates shape representation by object parts abstracted from results of instance and semantic segmentation. Promising shape representations enable computers to interpret a shape with meaningful parts and…
Modern processor architectures, in addition to having still more cores, also require still more consideration to memory-layout in order to run at full capacity. The usefulness of most languages is deprecating as their abstractions,…
While linear attention architectures offer efficient inference, compressing unbounded history into a fixed-size memory inherently limits expressivity and causes information loss. To address this limitation, we introduce Random Access Memory…
The program performance on modern hardware is characterized by \emph{locality of reference}, that is, it is faster to access data that is close in address space to data that has been accessed recently than data in a random location. This is…
Current compilers implement security features and optimizations that require nontrivial semantic reasoning about pointers and memory allocation: the program after the insertion of the security feature, or after applying the optimization,…
Based on the tremendous success of pre-trained language models (PrLMs) for source code comprehension tasks, current literature studies either ways to further improve the performance (generalization) of PrLMs, or their robustness against…
Concurrency theory has received considerable attention, but mostly in the scope of synchronous process algebras such as CCS, CSP, and ACP. As another way of handling concurrency, data-based coordination languages aim to provide a clear…
Most programs compiled to WebAssembly (Wasm) today are written in unsafe languages like C and C++. Unfortunately, memory-unsafe C code remains unsafe when compiled to Wasm -- and attackers can exploit buffer overflows and use-after-frees in…
Poor time predictability of multicore processors has been a long-standing challenge in the real-time systems community. In this paper, we make a case that a fundamental problem that prevents efficient and predictable real-time computing on…
We present a type-based analysis ensuring memory safety and object protocol completion in the Java-like language Mungo. Objects are annotated with usages, typestates-like specifications of the admissible sequences of method calls. The…
In neural architecture search (NAS), the space of neural network architectures is automatically explored to maximize predictive accuracy for a given task. Despite the success of recent approaches, most existing methods cannot be directly…
Position representation is crucial for building position-aware representations in Transformers. Existing position representations suffer from a lack of generalization to test data with unseen lengths or high computational cost. We…
Abstraction of a continuous-space model into a finite state and input dynamical model is a key step in formal controller synthesis tools. To date, these software tools have been limited to systems of modest size (typically $\leq$ 6…
Existing Neural Architecture Search (NAS) methods either encode neural architectures using discrete encodings that do not scale well, or adopt supervised learning-based methods to jointly learn architecture representations and optimize…